E

requirements.txt

@@ -0,0 +1,65 @@
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.2.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+fastapi==0.109.2
+ffmpy==0.3.2
+filelock==3.13.1
+fonttools==4.48.1
+fsspec==2024.2.0
+gradio==4.18.0
+gradio_client==0.10.0
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.26.0
+huggingface-hub==0.20.3
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.2
+mdurl==0.1.2
+numpy==1.26.4
+orjson==3.9.13
+packaging==23.2
+pandas==2.2.0
+pillow==10.2.0
+pydantic==2.6.1
+pydantic_core==2.16.2
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.33.0
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.17.1
+ruff==0.2.1
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+starlette==0.36.3
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.2
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2024.1
+urllib3==2.2.0
+uvicorn==0.27.1
+websockets==11.0.3

src/engines/TTSEngine/CoquiTTSEngine.py

@@ -89,23 +89,31 @@ class CoquiTTSEngine(BaseTTSEngine):
         "hi",  # Hindi
     ]
     options = [
-        gr.Dropdown(
-            voices, value=voices[0], label="voice", max_choices=1
-        ),
-        gr.Dropwdown(
-            languages, value=languages[0], label="language", max_choices=1
-        ),
+        {
+            "type": "dropdown",
+            "label": "Voice",
+            "choices": voices,
+            "max": 1,
+        },
+        {
+            "type": "dropdown",
+            "label": "Language",
+            "choices": languages,
+            "max": 1,
+        },
     ]
-    def __init__(self):
+
+    def __init__(self, options: list):
         super().__init__()
 
+        self.voice = options[0][0]
+        self.language = options[1][0]
+
         os.environ["COQUI_TOS_AGREED"] = "1"
         self.tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2")
         device = "cuda" if torch.cuda.is_available() else "cpu"
         self.tts.to(device)
 
     def synthesize(self, text: str, path: str) -> str:
-        voice = self.options[0].value
-        language = self.options[1].value
-        self.tts.tts_to_file(text=text, file_path=path, lang=language, speaker=voice)
+        self.tts.tts_to_file(text=text, file_path=path, lang=self.language, speaker=self.voice)
         return path

src/engines/TTSEngine/ElevenLabsTTSEngine.py

@@ -1,12 +1,37 @@
-from .BaseTTSEngine import AbstractTTSEngine
+from .BaseTTSEngine import BaseTTSEngine
 import gradio as gr
 
-class ElevenLabsTTSEngine(AbstractTTSEngine):
-    options = [gr.Radio(["Neutral", "Happy", "Sad"], label="emotion")]
+class ElevenLabsTTSEngine(BaseTTSEngine):
+    options = [
+        {
+            "type": "dropdown",
+            "label": "Voice",
+            "choices": [
+                "Zofija Kendrick",
+                "Narelle Moon",
+                "Barbora MacLean",
+                "Alexandra Hisakawa",
+                "Alma María",
+                "Rosemary Okafor",
+                "Ige Behringer",
+                "Filip Traverse",
+                "Damjan Chapman",
+                "Wulf Carlevaro",
+                "Aaron Dreschner",
+                "Kumar Dahl",
+                "Eugenio Mataracı",
+                "Ferran Simen",
+                "Xavier Hayasaka",
+                "Luis Moray",
+                "Marcos Rudaski",
+            ],
+        }
+    ]
     name = "ElevenLabs"
     description = "ElevenLabs TTS engine."
 
-    def __init__(self):
+    def __init__(self, options: list[list | tuple | str | int | float | bool | None]):
+        self.voice = options[0][0]
         super().__init__()
 
     def synthesize(self, text: str, path: str) -> str: